arXiv subjects

Liang Zheng

Publications and source records attributed to Liang Zheng.

At least 163 records · Page 9Linked to original sources

arXiv2020

Study of nuclear modification factors of (anti-)hadrons and light (anti-)nuclei in Pb-Pb collisions at $\sqrt{s_{\rm{NN}}}$ = 2.76 TeV

The nuclear modification factors ($R_{AA}$) of $π^{\pm}, p(\bar p)$, and $d(\bar d)$ with $|y|<0.5, p_T<20.0$~GeV/c in peripheral (40-60\%) and central (0-5\%) Pb-Pb collisions at $\sqrt {s_{NN}}=2.76$ TeV have been studied using the parton and hadron cascade ({\footnotesize PACIAE}) model plus the dynamically constrained phase space coalescence ({\footnotesize DCPC}) model. It is found that the $R_{AA}$ of light (anti)nuclei ($d, \bar d$) is similar to that of hadrons ($π^\pm, p, \bar p$), and the $R_{AA}$ of antiparticles is the same as that of particles. The suppression of $R_{AA}$ at high-$p_T$ strongly depends on event centrality and mass of the particles, i.e., the central collision is more suppressed than the peripheral collision. Besides, the yield ratios and double ratios for different particle species in $pp$ and Pb-Pb collisions are discussed, respectively. It is observed that the yield ratios and double ratios of $d$ to $p$ and $p$ to $π$ are similar to those of their anti-particles in three different collision systems, suggesting that the suppressions of matter ($π^{+}, p, d$) and the corresponding antimatter ($π^{-},\bar{p},\bar{d}$) are around the same level.

hep-ph↗

arXiv2020

Towards a qualitative hadron-parton correspondence in the nuclear modification factor

In this work, we propose a method to show the correspondence between hadron and its quark component nuclear modification factors. A parton and hadron cascade model PACIAE based on the PYTHIA6.4 is employed to calculate the hadron and its quark component nuclear modification factors in the 0-5\% most central $Pb+Pb$ collisions at $\sqrt{s_{NN}}$=2.76 TeV. It turns out that the hadron nuclear modification factor is usually smaller than that of its quark component. On the other hand, it is shown in our study that the "dead cone effect" is more likely to be identified with the quarks and mesons but not with the baryon states obviously.

nucl-th↗

arXiv2020

Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval

Most existing works of adversarial samples focus on attacking image recognition models, while little attention is paid to the image retrieval task. In this paper, we identify two inherent challenges in applying prevailing image recognition attack methods to image retrieval. First, image retrieval demands discriminative visual features, which is significantly different from the one-hot class prediction in image recognition. Second, due to the disjoint and potentially unrelated classes between the training and test set in image retrieval, predicting the query category from predefined training classes is not accurate and leads to a sub-optimal adversarial gradient. To address these limitations, we propose a new white-box attack approach, Opposite-Direction Feature Attack (ODFA), to generate adversarial queries. Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space. To our knowledge, we are among the early attempts to design an attack method specifically for image retrieval. When we deploy an attacked image as the query, the true matches are prone to receive low ranks. We demonstrate through extensive experiments that (1) only crafting adversarial queries is sufficient to fool the state-of-the-art retrieval systems; (2) the proposed attack method, ODFA, leads to a higher attack success rate than classification attack methods, validating the necessity of leveraging characteristics of image retrieval; (3) the adversarial queries generated by our method have good transferability to other retrieval models without accessing their parameters, i.e.,the black-box setting.

cs.CV↗

arXiv2020

Simulating Content Consistent Vehicle Datasets with Attribute Descent

This paper uses a graphic engine to simulate a large amount of training data with free annotations. Between synthetic and real data, there is a two-level domain gap, i.e., content level and appearance level. While the latter has been widely studied, we focus on reducing the content gap in attributes like illumination and viewpoint. To reduce the problem complexity, we choose a smaller and more controllable application, vehicle re-identification (re-ID). We introduce a large-scale synthetic dataset VehicleX. Created in Unity, it contains 1,362 vehicles of various 3D models with fully editable attributes. We propose an attribute descent approach to let VehicleX approximate the attributes in real-world datasets. Specifically, we manipulate each attribute in VehicleX, aiming to minimize the discrepancy between VehicleX and real data in terms of the Fréchet Inception Distance (FID). This attribute descent algorithm allows content domain adaptation (DA) orthogonal to existing appearance DA methods. We mix the optimized VehicleX data with real-world vehicle re-ID datasets, and observe consistent improvement. With the augmented datasets, we report competitive accuracy. We make the dataset, engine and our codes available at https://github.com/yorkeyao/VehicleX.

cs.CV↗

arXiv2020

Learning Object Relation Graph and Tentative Policy for Visual Navigation

Target-driven visual navigation aims at navigating an agent towards a given target based on the observation of the agent. In this task, it is critical to learn informative visual representation and robust navigation policy. Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN). ORG improves visual representation learning by integrating object relationships, including category closeness and spatial correlations, e.g., a TV usually co-occurs with a remote spatially. Both Trial-driven IL and TPN underlie robust navigation policy, instructing the agent to escape from deadlock states, such as looping or being stuck. Specifically, trial-driven IL is a type of supervision used in policy network training, while TPN, mimicking the IL supervision in unseen environment, is applied in testing. Experiment in the artificial environment AI2-Thor validates that each of the techniques is effective. When combined, the techniques bring significantly improvement over baseline methods in navigation effectiveness and efficiency in unseen environments. We report 22.8% and 23.5% increase in success rate and Success weighted by Path Length (SPL), respectively. The code is available at https://github.com/xiaobaishu0097/ECCV-VN.git.

cs.CV↗

arXiv2020

Study on the $Ω_{c}^{0}$ States Decaying to $Ξ_{c}^{+}K^{-}$ in $pp$ collisions at $\sqrt{s}=7$, 13 TeV

The production of strange particles $Ξ_{c}^{+}, K^{-}$ is simulated in mid-rapidity $pp$ collisions at $\sqrt{s}=7$ TeV with $0.2 \leq pt \leq 6$~GeV/c using the {\footnotesize PACIAE} model. The results are consistent with LHCb experimental data on $Ξ_{c}^{+}$ and $K^{-}$ yield. Then, a dynamically constrained phase-space coalescence ({\footnotesize DCPC}) model plus {\footnotesize PACIAE} model was used to produce the $Ξ_{c}^{+}K^{-}$ bound states and study the narrow excited $Ω_{c}^{0}$ states through $Ω_{c}^{0} \to Ξ_{c}^{+}K^{-}$ in $pp$ collisions at $\sqrt{s}=7$ and 13 TeV. The yield, transverse momentum distribution, and rapidity distribution of the five new excited $Ω_{c}^{0}$ states of $Ω_{c}(3000)^{0}$, $Ω_{c}(3050)^{0}$, $Ω_{c}(3066)^{0}$,$Ω_{c}(3090)^{0}$and $Ω_{c}(3119)^{0}$ were predicted.

hep-ph↗

arXiv2020

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering. A potential drawback of using pseudo labels is that errors may accumulate and it is challenging to estimate the number of pseudo IDs. We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels. The goal is to construct a self-supervised pretext task that matches the person re-ID objective. Inspired by the \emph{data association} concept in multi-object tracking, we propose the \textbf{Cyc}le \textbf{As}sociation (\textbf{CycAs}) task: after performing data association between a pair of video frames forward and then backward, a pedestrian instance is supposed to be associated to itself. To fulfill this goal, the model must learn a meaningful representation that can well describe correspondences between instances in frame pairs. We adapt the discrete association process to a differentiable form, such that end-to-end training becomes feasible. Experiments are conducted in two aspects: We first compare our method with existing unsupervised re-ID methods on seven benchmarks and demonstrate CycAs' superiority. Then, to further validate the practical value of CycAs in real-world applications, we perform training on self-collected videos and report promising performance on standard test sets.

cs.CV↗

arXiv2020

Towards Real-Time Multi-Object Tracking

Modern multiple object tracking (MOT) systems usually follow the \emph{tracking-by-detection} paradigm. It has 1) a detection model for target localization and 2) an appearance embedding model for data association. Having the two models separately executed might lead to efficiency problems, as the running time is simply a sum of the two steps without investigating potential structures that can be shared between them. Existing research efforts on real-time MOT usually focus on the association step, so they are essentially real-time association methods but not real-time MOT system. In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model. Specifically, we incorporate the appearance embedding model into a single-shot detector, such that the model can simultaneously output detections and the corresponding embeddings. We further propose a simple and fast association method that works in conjunction with the joint model. In both components the computation cost is significantly reduced compared with former MOT systems, resulting in a neat and fast baseline for future follow-ups on real-time MOT algorithm design. To our knowledge, this work reports the first (near) real-time MOT system, with a running speed of 22 to 40 FPS depending on the input resolution. Meanwhile, its tracking accuracy is comparable to the state-of-the-art trackers embodying separate detection and embedding (SDE) learning ($64.4\%$ MOTA \vs $66.1\%$ MOTA on MOT-16 challenge). Code and models are available at \url{https://github.com/Zhongdao/Towards-Realtime-MOT}.

cs.CV↗

arXiv2020

Learning to simulate complex scenes

Data simulation engines like Unity are becoming an increasingly important data source that allows us to acquire ground truth labels conveniently. Moreover, we can flexibly edit the content of an image in the engine, such as objects (position, orientation) and environments (illumination, occlusion). When using simulated data as training sets, its editable content can be leveraged to mimic the distribution of real-world data, and thus reduce the content difference between the synthetic and real domains. This paper explores content adaptation in the context of semantic segmentation, where the complex street scenes are fully synthesized using 19 classes of virtual objects from a first person driver perspective and controlled by 23 attributes. To optimize the attribute values and obtain a training set of similar content to real-world data, we propose a scalable discretization-and-relaxation (SDR) approach. Under a reinforcement learning framework, we formulate attribute optimization as a random-to-optimized mapping problem using a neural network. Our method has three characteristics. 1) Instead of editing attributes of individual objects, we focus on global attributes that have large influence on the scene structure, such as object density and illumination. 2) Attributes are quantized to discrete values, so as to reduce search space and training complexity. 3) Correlated attributes are jointly optimized in a group, so as to avoid meaningless scene structures and find better convergence points. Experiment shows our system can generate reasonable and useful scenes, from which we obtain promising real-world segmentation accuracy compared with existing synthetic training sets.

cs.CV↗

arXiv2020

Circle Loss: A Unified Perspective of Pair Similarity Optimization

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$. We find a majority of loss functions, including the triplet loss and the softmax plus cross-entropy loss, embed $s_n$ and $s_p$ into similarity pairs and seek to reduce $(s_n-s_p)$. Such an optimization manner is inflexible, because the penalty strength on every single similarity score is restricted to be equal. Our intuition is that if a similarity score deviates far from the optimum, it should be emphasized. To this end, we simply re-weight each similarity to highlight the less-optimized similarity scores. It results in a Circle loss, which is named due to its circular decision boundary. The Circle loss has a unified formula for two elemental deep feature learning approaches, i.e. learning with class-level labels and pair-wise labels. Analytically, we show that the Circle loss offers a more flexible optimization approach towards a more definite convergence target, compared with the loss functions optimizing $(s_n-s_p)$. Experimentally, we demonstrate the superiority of the Circle loss on a variety of deep feature learning tasks. On face recognition, person re-identification, as well as several fine-grained image retrieval datasets, the achieved performance is on par with the state of the art.

cs.CV↗

arXiv2020

Impact of single string structure and multiple string interaction on strangeness production in Pb+Pb collisions at $\sqrt{S_{NN}} = 2.76$ TeV

We present a systematic study on the strange and multi-strange particles production in Pb+Pb collisions at $\sqrt{S_{NN}} = 2.76$ TeV based on the PACIAE model simulations. Two different mechanisms, namely the single string structure variations and multiple string interactions, are implemented in the simulations. These modifications give rise to an enhancement of the string tension value involved in the Lund string fragmentation framework and generate more strange particles in the hadronic final state. By comparing the simulation results with the ALICE experimental data, it turns out that the inclusion of the variable effective string tension in the PACIAE model is capable to reach an improved agreement between theory and experiment on the strangeness production in Pb+Pb collisions.

nucl-th↗

arXiv2020

Probing short-range correlations in the deuteron via incoherent diffractive $J/ψ$ production with spectator tagging at the EIC

Understanding the role of Quantum Chromodynamics in generating nuclear forces is important for uncovering the mechanism of short-ranged nuclear interactions and their manifestation in short range correlations (SRC). The future Electron-Ion-Collider (EIC) at Brookhaven National Laboratory in the US will provide an unprecedented opportunity to systematically investigate the underlying physics of SRC for energies and kinematic regions that are otherwise impossible to reach. We study SRCs in electron-deuteron scattering events using the Monte Carlo event generator BeAGLE. Specifically, we investigate the sensitivity of observables to high internal nucleon momentum in incoherent diffractive $J/ψ$ vector meson production. In a plane wave impulse approximation, the initial state deuteron wavefunction can be accessed directly from the four-momentum of the spectator nucleon. We use realistic physics simulations and far-forward detector simulations of the EIC to fully reveal the physics potential of this exclusive process. In particular, we provide the luminosity and detector requirements necessary to study SRCs in the deuteron at an EIC.

nucl-ex↗

arXiv2020

Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning

Training deep reinforcement learning agents on environments with multiple levels / scenes / conditions from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to the real world. While such a strategy is helpful with generalization, the use of multiple scenes significantly increases the variance of samples collected for policy gradient computations. Current methods continue to view this collection of scenes as a single Markov Decision Process (MDP) with a common value function; however, we argue that it is better to treat the collection as a single environment with multiple underlying MDPs. To this end, we propose a dynamic value estimation (DVE) technique for these multiple-MDP environments, motivated by the clustering effect observed in the value function distribution across different scenes. The resulting agent is able to learn a more accurate and scene-specific value function estimate (and hence the advantage function), leading to a lower sample variance. Our proposed approach is simple to accommodate with several existing implementations (like PPO, A3C) and results in consistent improvements for a range of ProcGen environments and the AI2-THOR framework based visual navigation task.

cs.LG↗

arXiv2020

Correlating Edge, Pose with Parsing

According to existing studies, human body edge and pose are two beneficial factors to human parsing. The effectiveness of each of the high-level features (edge and pose) is confirmed through the concatenation of their features with the parsing features. Driven by the insights, this paper studies how human semantic boundaries and keypoint locations can jointly improve human parsing. Compared with the existing practice of feature concatenation, we find that uncovering the correlation among the three factors is a superior way of leveraging the pivotal contextual cues provided by edges and poses. To capture such correlations, we propose a Correlation Parsing Machine (CorrPM) employing a heterogeneous non-local block to discover the spatial affinity among feature maps from the edge, pose and parsing. The proposed CorrPM allows us to report new state-of-the-art accuracy on three human parsing datasets. Importantly, comparative studies confirm the advantages of feature correlation over the concatenation.

cs.CV↗

arXiv2020

The 4th AI City Challenge

The AI City Challenge was created to accelerate intelligent video analysis that helps make cities smarter and safer. Transportation is one of the largest segments that can benefit from actionable insights derived from data captured by sensors, where computer vision and deep learning have shown promise in achieving large-scale practical deployment. The 4th annual edition of the AI City Challenge has attracted 315 participating teams across 37 countries, who leveraged city-scale real traffic data and high-quality synthetic data to compete in four challenge tracks. Track 1 addressed video-based automatic vehicle counting, where the evaluation is conducted on both algorithmic effectiveness and computational efficiency. Track 2 addressed city-scale vehicle re-identification with augmented synthetic data to substantially increase the training set for the task. Track 3 addressed city-scale multi-target multi-camera vehicle tracking. Track 4 addressed traffic anomaly detection. The evaluation system shows two leader boards, in which a general leader board shows all submitted results, and a public leader board shows results limited to our contest participation rules, that teams are not allowed to use external data in their work. The public leader board shows results more close to real-world situations where annotated data are limited. Our results show promise that AI technology can enable smarter and safer transportation systems.

cs.CV↗

arXiv2020

Hysteresis in anesthesia and recovery: Experimental observation and dynamical mechanism

The dynamical mechanism underlying the processes of anesthesia-induced loss of consciousness and recovery is key to gaining insights into the working of the nervous system. Previous experiments revealed an asymmetry between neural signals during the anesthesia and recovery processes. Here we obtain experimental evidence for the hysteresis loop and articulate the dynamical mechanism based on percolation on multilayer complex networks with self-similarity. Model analysis reveals that, during anesthesia, the network is able to maintain its neural pathways despite the loss of a substantial fraction of the edges. A predictive and potentially testable result is that, in the forward process of anesthesia, the average shortest path and the clustering coefficient of the neural network are markedly smaller than those associated with the recovery process. This suggests that the network strives to maintain certain neurological functions by adapting to a relatively more compact structure in response to anesthesia.

q-bio.NC↗

arXiv2020

Reliable coherent optical memory based on a laser-written waveguide

$\mathrm {^{151}Eu^{3+}}$-doped yttrium silicate ($\mathrm {^{151}Eu^{3+}:Y_2SiO_5}$ ) crystal is a unique material that possesses hyperfine states with coherence time up to 6 h. Many efforts have been devoted to the development of this material as optical quantum memories based on the bulk crystals, but integrable structures (such as optical waveguides) that can promote $\mathrm {^{151}Eu^{3+}:Y_2SiO_5}$-based quantum memories to practical applications, have not been demonstrated so far. Here we report the fabrication of type 2 waveguides in a $\mathrm {^{151}Eu^{3+}:Y_2SiO_5}$ crystal using femtosecond-laser micromachining. The resulting waveguides are compatible with single-mode fibers and have the smallest insertion loss of $4.95\ dB$. On-demand light storage is demonstrated in a waveguide by employing the spin-wave atomic frequency comb (AFC) scheme and the revival of silenced echo (ROSE) scheme. We implement a series of interference experiments based on these two schemes to characterize the storage fidelity. Interference visibility of the readout pulse is $0.99\pm 0.03$ for the spin-wave AFC scheme and $0.97\pm 0.02$ for the ROSE scheme, demonstrating the reliability of the integrated optical memory.

quant-ph↗

arXiv2020

Similarity-preserving Image-image Domain Adaptation for Person Re-identification

This article studies the domain adaptation problem in person re-identification (re-ID) under a "learning via translation" framework, consisting of two components, 1) translating the labeled images from the source to the target domain in an unsupervised manner, 2) learning a re-ID model using the translated images. The objective is to preserve the underlying human identity information after image translation, so that translated images with labels are effective for feature learning on the target domain. To this end, we propose a similarity preserving generative adversarial network (SPGAN) and its end-to-end trainable version, eSPGAN. Both aiming at similarity preserving, SPGAN enforces this property by heuristic constraints, while eSPGAN does so by optimally facilitating the re-ID model learning. More specifically, SPGAN separately undertakes the two components in the "learning via translation" framework. It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image. It then learns a re-ID model using existing networks. In comparison, eSPGAN seamlessly integrates image translation and re-ID model learning. During the end-to-end training of eSPGAN, re-ID learning guides image translation to preserve the underlying identity information of an image. Meanwhile, image translation improves re-ID learning by providing identity-preserving training samples of the target domain style. In the experiment, we show that identities of the fake images generated by SPGAN and eSPGAN are well preserved. Based on this, we report the new state-of-the-art domain adaptation results on two large-scale person re-ID datasets.

cs.CV↗